Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4758 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.8475. Min Act: -0.1700
Data Index: 5337139 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.6913. Min Act: -0.1700
Data Index: 2547044 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.6288. Min Act: -0.1700
Data Index: 8249658 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5663. Min Act: -0.1700
Data Index: 252916 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5350. Min Act: -0.1700
Data Index: 1102809 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5038. Min Act: -0.1700
Data Index: 8711758 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4725. Min Act: -0.1700
Data Index: 8351652 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5038. Min Act: -0.1700
Data Index: 4066301 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.5038. Min Act: -0.1700
Data Index: 7289859 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4413. Min Act: -0.1700
Data Index: 4066903 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4413. Min Act: -0.1700
Data Index: 6803427 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 1812822 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3788. Min Act: -0.1700
Data Index: 5034841 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.4100. Min Act: -0.1700
Data Index: 7349482 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3788. Min Act: -0.1700
Data Index: 8750825 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3475. Min Act: -0.1700
Data Index: 1712564 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3475. Min Act: -0.1700
Data Index: 6511901 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3163. Min Act: -0.1700
Data Index: 3940493 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.3163. Min Act: -0.1700
Data Index: 610849 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8475. Min Range: -6.8475
Max Act: 6.2850. Min Act: -0.1700
Data Index: 4315907 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19